← Authors

Tor Lattimore

61 papers · 2013–2025 · 10 conferences · across top CS/AI conferences

Achievements

๐Ÿƒ Academic Marathon (12) ๐ŸŒ‰ Interdisciplinary Bridge ๐Ÿ Cross-Pollinator (10) ๐Ÿ—บ๏ธ Taxonomy Completionist (17) ๐Ÿงญ Keyword Pioneer ๐Ÿฃ Hot Topic Early Bird ๐ŸŒˆ Renaissance Researcher (5) ๐ŸŒ Conference Polyglot (10) ๐Ÿ  Conference Loyalist (22) ๐Ÿบ Lone Wolf (6) ๐Ÿ† Grand Slam ๐Ÿ”ฌ Deep Specialist (26) ๐Ÿ† Keyword Champion (3) ๐Ÿค Dynamic Duo (22) ๐Ÿ‘‘ Triple Crown ๐Ÿ—ƒ๏ธ Keyword Collector (187) โ“ The Questioner โšก Prolific Year (9) ๐Ÿš€ Conference Pioneer ๐Ÿ“ˆ Trend Setter ๐Ÿ’Ž Century Club (61) ๐Ÿ”ฅ Unstoppable (13)

Conferences

NIPS (22) COLT (13) ICML (11) AISTATS (3) JMLR (3) UAI (3) ALT (2) IJCAI (2) AAAI (1) ICLR (1)

Top co-authors

Csaba Szepesvรกri (22) Botao Hao (9) Andrรกs Gyรถrgy (6) Laurent Orseau (4) Julian Zimmert (3) Marcus Hutter (3) Eren Sezener (3) Mengdi Wang (3) Branislav Kveton (3) Johannes Kirschner (3)

Keywords

regret bound (35) online learning (18) multi-armed bandit (18) contextual bandit (8) linear bandit (7) thompson sampling (7) partial monitoring (6) adversarial bandit (6) reinforcement learning (5) minimax regret (5) stochastic bandit (5) bayesian regret (5) stochastic optimization (5) regret minimization (4) online algorithm (4) adversarial setting (3) zeroth-order optimization (3) learning to rank (3) bayesian inference (3) sample complexity (3)

Papers

Thompson Sampling for Bandit Convex Optimisation COLT 2025
Online Newton Method for Bandit Convex Optimisation Extended Abstract COLT 2024
Context-lumpable stochastic bandits NIPS 2023
Probabilistic Inference in Reinforcement Learning Done Right NIPS 2023
Leveraging Demonstrations to Improve Online Learning: Quality Matters ICML 2023
Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost ICML 2023
Linear Partial Monitoring for Sequential Decision Making: Algorithms, Regret Bounds and Applications JMLR 2023
A Second-Order Method for Stochastic Bandit Convex Optimisation COLT 2023
A Lower Bound for Linear and Kernel Regression with Adaptive Covariates COLT 2023
Minimax Regret for Partial Monitoring: Infinite Outcomes and Rustichiniโ€™s Regret COLT 2022
Contextual Information-Directed Sampling ICML 2022
Return of the bias: Almost minimax optimal high probability bounds for adversarial linear bandits COLT 2022
Regret Bounds for Information-Directed Reinforcement Learning NIPS 2022
Matrix games with bandit feedback UAI 2021
On the Optimality of Batch Policy Optimization Algorithms ICML 2021
Asymptotically Optimal Information-Directed Sampling COLT 2021
Variational Bayesian Optimistic Sampling NIPS 2021
Information Directed Sampling for Sparse Linear Bandits NIPS 2021
Bandit Phase Retrieval NIPS 2021
Online Sparse Reinforcement Learning AISTATS 2021
Improved Regret for Zeroth-Order Stochastic Convex Bandits COLT 2021
Mirror Descent and the Information Ratio COLT 2021
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient ICML 2021
Gated Linear Networks AAAI 2021
Learning with Good Feature Representations in Bandits and in RL with a Generative Model ICML 2020
Model Selection in Contextual Stochastic Bandit Problems NIPS 2020
High-Dimensional Sparse Linear Bandits NIPS 2020
Gaussian Gated Linear Networks NIPS 2020
Adaptive Exploration in Linear Contextual Bandit AISTATS 2020
Information Directed Sampling for Linear Partial Monitoring COLT 2020
Exploration by Optimisation in Partial Monitoring COLT 2020
Behaviour Suite for Reinforcement Learning ICLR 2020
Linear bandits with Stochastic Delayed Feedback ICML 2020
Connections Between Mirror Descent, Thompson Sampling and the Information Ratio NIPS 2019
Iterative Budgeted Exponential Search IJCAI 2019
On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits UAI 2019
Cleaning up the neighborhood: A full classification for adversarial partial monitoring ALT 2019
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits ICML 2019
Online Learning to Rank with Features ICML 2019
BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback UAI 2019
An Information-Theoretic Approach to Minimax Regret in Partial Monitoring COLT 2019
A Geometric Perspective on Optimal Representations for Reinforcement Learning NIPS 2019
Single-Agent Policy Tree Search With Guarantees NIPS 2018
TopRank: A practical algorithm for online stochastic ranking NIPS 2018
Refining the Confidence Level for Optimistic Bandit Strategies JMLR 2018
Following the Leader and Fast Rates in Online Linear Prediction: Curved Constraint Sets and Other Regularities JMLR 2017
A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis NIPS 2017
The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits AISTATS 2017
Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning NIPS 2017
On Thompson Sampling and Asymptotic Optimality IJCAI 2017
Soft-Bayes: Prod for Mixtures of Experts with Log-Loss ALT 2017
Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits COLT 2016
Conservative Bandits ICML 2016
On Explore-Then-Commit strategies NIPS 2016
Causal Bandits: Learning Good Interventions via Causal Inference NIPS 2016
Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities NIPS 2016
Refined Lower Bounds for Adversarial Bandits NIPS 2016
The Pareto Regret Frontier for Bandits NIPS 2015
Linear Multi-Resource Allocation with Semi-Bandit Feedback NIPS 2015
Bounded Regret for Finite-Armed Structured Bandits NIPS 2014
The Sample-Complexity of General Reinforcement Learning ICML 2013